[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH for-4.1 v2 06/13] tcg/ppc: Initial backend support f
|
From: |
Richard Henderson |
|
Subject: |
[Qemu-devel] [PATCH for-4.1 v2 06/13] tcg/ppc: Initial backend support for Altivec |
|
Date: |
Sun, 17 Mar 2019 02:08:27 -0700 |
There are a few missing operations yet, like expansion of
multiply and shifts. But this has move, load, store, and
basic arithmetic.
Signed-off-by: Richard Henderson <address@hidden>
---
tcg/ppc/tcg-target.h | 31 +-
tcg/ppc/tcg-target.opc.h | 3 +
tcg/ppc/tcg-target.inc.c | 609 +++++++++++++++++++++++++++++++++++----
3 files changed, 584 insertions(+), 59 deletions(-)
create mode 100644 tcg/ppc/tcg-target.opc.h
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 52c1bb04b1..683eb807ae 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -31,7 +31,7 @@
# define TCG_TARGET_REG_BITS 32
#endif
-#define TCG_TARGET_NB_REGS 32
+#define TCG_TARGET_NB_REGS 64
#define TCG_TARGET_INSN_UNIT_SIZE 4
#define TCG_TARGET_TLB_DISPLACEMENT_BITS 16
@@ -45,10 +45,20 @@ typedef enum {
TCG_REG_R24, TCG_REG_R25, TCG_REG_R26, TCG_REG_R27,
TCG_REG_R28, TCG_REG_R29, TCG_REG_R30, TCG_REG_R31,
+ TCG_REG_V0, TCG_REG_V1, TCG_REG_V2, TCG_REG_V3,
+ TCG_REG_V4, TCG_REG_V5, TCG_REG_V6, TCG_REG_V7,
+ TCG_REG_V8, TCG_REG_V9, TCG_REG_V10, TCG_REG_V11,
+ TCG_REG_V12, TCG_REG_V13, TCG_REG_V14, TCG_REG_V15,
+ TCG_REG_V16, TCG_REG_V17, TCG_REG_V18, TCG_REG_V19,
+ TCG_REG_V20, TCG_REG_V21, TCG_REG_V22, TCG_REG_V23,
+ TCG_REG_V24, TCG_REG_V25, TCG_REG_V26, TCG_REG_V27,
+ TCG_REG_V28, TCG_REG_V29, TCG_REG_V30, TCG_REG_V31,
+
TCG_REG_CALL_STACK = TCG_REG_R1,
TCG_AREG0 = TCG_REG_R27
} TCGReg;
+extern bool have_isa_altivec;
extern bool have_isa_2_06;
extern bool have_isa_3_00;
@@ -124,6 +134,25 @@ extern bool have_isa_3_00;
#define TCG_TARGET_HAS_mulsh_i64 1
#endif
+/* ??? Constant pool not yet supported for 32-bit. */
+#if TCG_TARGET_REG_BITS == 64
+#define TCG_TARGET_HAS_v64 have_isa_altivec
+#define TCG_TARGET_HAS_v128 have_isa_altivec
+#define TCG_TARGET_HAS_v256 0
+#endif
+
+#define TCG_TARGET_HAS_andc_vec 1
+#define TCG_TARGET_HAS_orc_vec 0
+#define TCG_TARGET_HAS_not_vec 1
+#define TCG_TARGET_HAS_neg_vec 0
+#define TCG_TARGET_HAS_shi_vec 0
+#define TCG_TARGET_HAS_shs_vec 0
+#define TCG_TARGET_HAS_shv_vec 0
+#define TCG_TARGET_HAS_cmp_vec 1
+#define TCG_TARGET_HAS_mul_vec 1
+#define TCG_TARGET_HAS_sat_vec 1
+#define TCG_TARGET_HAS_minmax_vec 1
+
void flush_icache_range(uintptr_t start, uintptr_t stop);
void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t);
diff --git a/tcg/ppc/tcg-target.opc.h b/tcg/ppc/tcg-target.opc.h
new file mode 100644
index 0000000000..4816a6c3d4
--- /dev/null
+++ b/tcg/ppc/tcg-target.opc.h
@@ -0,0 +1,3 @@
+/* Target-specific opcodes for host vector expansion. These will be
+ emitted by tcg_expand_vec_op. For those familiar with GCC internals,
+ consider these to be UNSPEC with names. */
diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index ec8e336be8..61a245b828 100644
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -42,6 +42,9 @@
# define TCG_REG_TMP1 TCG_REG_R12
#endif
+#define TCG_VEC_TMP1 TCG_REG_V0
+#define TCG_VEC_TMP2 TCG_REG_V1
+
#define TCG_REG_TB TCG_REG_R31
#define USE_REG_TB (TCG_TARGET_REG_BITS == 64)
@@ -61,6 +64,7 @@
static tcg_insn_unit *tb_ret_addr;
+bool have_isa_altivec;
bool have_isa_2_06;
bool have_isa_3_00;
@@ -72,39 +76,15 @@ bool have_isa_3_00;
#endif
#ifdef CONFIG_DEBUG_TCG
-static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
- "r0",
- "r1",
- "r2",
- "r3",
- "r4",
- "r5",
- "r6",
- "r7",
- "r8",
- "r9",
- "r10",
- "r11",
- "r12",
- "r13",
- "r14",
- "r15",
- "r16",
- "r17",
- "r18",
- "r19",
- "r20",
- "r21",
- "r22",
- "r23",
- "r24",
- "r25",
- "r26",
- "r27",
- "r28",
- "r29",
- "r30",
- "r31"
+static const char tcg_target_reg_names[TCG_TARGET_NB_REGS][4] = {
+ "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7",
+ "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
+ "r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23",
+ "r24", "r25", "r26", "r27", "r28", "r29", "r30", "r31",
+ "v0", "v1", "v2", "v3", "v4", "v5", "v6", "v7",
+ "v8", "v9", "v10", "v11", "v12", "v13", "v14", "v15",
+ "v16", "v17", "v18", "v19", "v20", "v21", "v22", "v23",
+ "v24", "v25", "v26", "v27", "v28", "v29", "v30", "v31",
};
#endif
@@ -139,6 +119,26 @@ static const int tcg_target_reg_alloc_order[] = {
TCG_REG_R5,
TCG_REG_R4,
TCG_REG_R3,
+
+ /* V0 and V1 reserved as temporaries; V20 - V31 are call-saved */
+ TCG_REG_V2, /* call clobbered, vectors */
+ TCG_REG_V3,
+ TCG_REG_V4,
+ TCG_REG_V5,
+ TCG_REG_V6,
+ TCG_REG_V7,
+ TCG_REG_V8,
+ TCG_REG_V9,
+ TCG_REG_V10,
+ TCG_REG_V11,
+ TCG_REG_V12,
+ TCG_REG_V13,
+ TCG_REG_V14,
+ TCG_REG_V15,
+ TCG_REG_V16,
+ TCG_REG_V17,
+ TCG_REG_V18,
+ TCG_REG_V19,
};
static const int tcg_target_call_iarg_regs[] = {
@@ -233,6 +233,10 @@ static const char
*target_parse_constraint(TCGArgConstraint *ct,
ct->ct |= TCG_CT_REG;
ct->u.regs = 0xffffffff;
break;
+ case 'v':
+ ct->ct |= TCG_CT_REG;
+ ct->u.regs = 0xffffffff00000000ull;
+ break;
case 'L': /* qemu_ld constraint */
ct->ct |= TCG_CT_REG;
ct->u.regs = 0xffffffff;
@@ -320,6 +324,7 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define XO31(opc) (OPCD(31)|((opc)<<1))
#define XO58(opc) (OPCD(58)|(opc))
#define XO62(opc) (OPCD(62)|(opc))
+#define VX4(opc) (OPCD(4)|(opc))
#define B OPCD( 18)
#define BC OPCD( 16)
@@ -461,6 +466,71 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define NOP ORI /* ori 0,0,0 */
+#define LVX XO31(103)
+#define LVEWX XO31(71)
+
+#define STVX XO31(231)
+#define STVEWX XO31(199)
+
+#define VADDSBS VX4(768)
+#define VADDUBS VX4(512)
+#define VADDUBM VX4(0)
+#define VADDSHS VX4(832)
+#define VADDUHS VX4(576)
+#define VADDUHM VX4(64)
+#define VADDSWS VX4(896)
+#define VADDUWS VX4(640)
+#define VADDUWM VX4(128)
+
+#define VSUBSBS VX4(1792)
+#define VSUBUBS VX4(1536)
+#define VSUBUBM VX4(1024)
+#define VSUBSHS VX4(1856)
+#define VSUBUHS VX4(1600)
+#define VSUBUHM VX4(1088)
+#define VSUBSWS VX4(1920)
+#define VSUBUWS VX4(1664)
+#define VSUBUWM VX4(1152)
+
+#define VMAXSB VX4(258)
+#define VMAXSH VX4(322)
+#define VMAXSW VX4(386)
+#define VMAXUB VX4(2)
+#define VMAXUH VX4(66)
+#define VMAXUW VX4(130)
+#define VMINSB VX4(770)
+#define VMINSH VX4(834)
+#define VMINSW VX4(898)
+#define VMINUB VX4(514)
+#define VMINUH VX4(578)
+#define VMINUW VX4(642)
+
+#define VCMPEQUB VX4(6)
+#define VCMPEQUH VX4(70)
+#define VCMPEQUW VX4(134)
+#define VCMPGTSB VX4(774)
+#define VCMPGTSH VX4(838)
+#define VCMPGTSW VX4(902)
+#define VCMPGTUB VX4(518)
+#define VCMPGTUH VX4(582)
+#define VCMPGTUW VX4(646)
+
+#define VAND VX4(1028)
+#define VANDC VX4(1092)
+#define VNOR VX4(1284)
+#define VOR VX4(1156)
+#define VXOR VX4(1220)
+
+#define VSPLTB VX4(524)
+#define VSPLTH VX4(588)
+#define VSPLTW VX4(652)
+#define VSPLTISB VX4(780)
+#define VSPLTISH VX4(844)
+#define VSPLTISW VX4(908)
+
+#define VPERM VX4(43)
+#define VSLDOI VX4(44)
+
#define RT(r) ((r)<<21)
#define RS(r) ((r)<<21)
#define RA(r) ((r)<<16)
@@ -473,6 +543,11 @@ static int tcg_target_const_match(tcg_target_long val,
TCGType type,
#define MB64(b) ((b)<<5)
#define FXM(b) (1 << (19 - (b)))
+#define VRT(r) (((r) & 31) << 21)
+#define VRA(r) (((r) & 31) << 16)
+#define VRB(r) (((r) & 31) << 11)
+#define VRC(r) (((r) & 31) << 6)
+
#define LK 1
#define TAB(t, a, b) (RT(t) | RA(a) | RB(b))
@@ -568,9 +643,29 @@ static void tcg_out_mem_long(TCGContext *s, int opi, int
opx, TCGReg rt,
static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
{
- tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
- if (ret != arg) {
- tcg_out32(s, OR | SAB(arg, ret, arg));
+ if (ret == arg) {
+ return true;
+ }
+ switch (type) {
+ case TCG_TYPE_I64:
+ tcg_debug_assert(TCG_TARGET_REG_BITS == 64);
+ /* fallthru */
+ case TCG_TYPE_I32:
+ if (ret < 32 && arg < 32) {
+ tcg_out32(s, OR | SAB(arg, ret, arg));
+ break;
+ } else if (ret < 32 || arg < 32) {
+ /* Altivec does not support vector/integer moves. */
+ return false;
+ }
+ /* fallthru */
+ case TCG_TYPE_V64:
+ case TCG_TYPE_V128:
+ tcg_debug_assert(ret >= 32 && arg >= 32);
+ tcg_out32(s, VOR | VRT(ret) | VRA(arg) | VRB(arg));
+ break;
+ default:
+ g_assert_not_reached();
}
return true;
}
@@ -720,10 +815,64 @@ static void tcg_out_movi_int(TCGContext *s, TCGType type,
TCGReg ret,
}
}
-static inline void tcg_out_movi(TCGContext *s, TCGType type, TCGReg ret,
- tcg_target_long arg)
+static void tcg_out_imm_vec(TCGContext *s, TCGReg ret,
+ uint64_t h, uint64_t l)
{
- tcg_out_movi_int(s, type, ret, arg, false);
+#ifndef HOST_WORDS_BIGENDIAN
+ uint64_t t = l; l = h; h = t;
+#endif
+
+ /* FIXME: 32-bit altivec */
+ new_pool_l2(s, R_PPC_ADDR16, s->code_ptr,
+ -(intptr_t)s->code_gen_ptr, h, l);
+ tcg_out32(s, ADDIS | TAI(TCG_REG_TMP1, TCG_REG_TB, 0));
+ tcg_out32(s, ADDI | TAI(TCG_REG_TMP1, TCG_REG_TMP1, 0));
+ tcg_out32(s, LVX | VRT(ret) | RB(TCG_REG_TMP1));
+}
+
+static void tcg_out_dupi_vec(TCGContext *s, TCGType type, TCGReg ret,
+ tcg_target_long val)
+{
+ int low = (int8_t)val;
+
+ if (low >= -16 && low < 16) {
+ if (val == (tcg_target_long)dup_const(MO_8, low)) {
+ tcg_out32(s, VSPLTISB | VRT(ret) | ((val & 31) << 16));
+ return;
+ }
+ if (val == (tcg_target_long)dup_const(MO_16, low)) {
+ tcg_out32(s, VSPLTISH | VRT(ret) | ((val & 31) << 16));
+ return;
+ }
+ if (val == (tcg_target_long)dup_const(MO_32, low)) {
+ tcg_out32(s, VSPLTISW | VRT(ret) | ((val & 31) << 16));
+ return;
+ }
+ }
+
+ /* With Altivec, we load the whole 128-bit value. */
+ tcg_out_imm_vec(s, ret, val, val);
+}
+
+static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg ret,
+ tcg_target_long arg)
+{
+ switch (type) {
+ case TCG_TYPE_I32:
+ case TCG_TYPE_I64:
+ tcg_debug_assert(ret < 32);
+ tcg_out_movi_int(s, type, ret, arg, false);
+ break;
+
+ case TCG_TYPE_V64:
+ case TCG_TYPE_V128:
+ tcg_debug_assert(ret >= 32);
+ tcg_out_dupi_vec(s, type, ret, arg);
+ break;
+
+ default:
+ g_assert_not_reached();
+ }
}
static bool mask_operand(uint32_t c, int *mb, int *me)
@@ -876,7 +1025,7 @@ static void tcg_out_mem_long(TCGContext *s, int opi, int
opx, TCGReg rt,
}
/* For unaligned, or very large offsets, use the indexed form. */
- if (offset & align || offset != (int32_t)offset) {
+ if (offset & align || offset != (int32_t)offset || opi == 0) {
if (rs == base) {
rs = TCG_REG_R0;
}
@@ -907,32 +1056,92 @@ static void tcg_out_mem_long(TCGContext *s, int opi, int
opx, TCGReg rt,
}
}
-static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
- TCGReg arg1, intptr_t arg2)
+static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
+ TCGReg base, intptr_t offset)
{
- int opi, opx;
+ int shift;
- tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
- if (type == TCG_TYPE_I32) {
- opi = LWZ, opx = LWZX;
- } else {
- opi = LD, opx = LDX;
+ switch (type) {
+ case TCG_TYPE_I32:
+ if (ret < 32) {
+ tcg_out_mem_long(s, LWZ, LWZX, ret, base, offset);
+ break;
+ }
+ assert((offset & 3) == 0);
+ tcg_out_mem_long(s, 0, LVEWX, ret & 31, base, offset);
+ shift = (offset - 4) & 0xc;
+ if (shift) {
+ tcg_out32(s, VSLDOI | VRT(ret) | VRA(ret) | VRB(ret)
+ | (shift << 6));
+ }
+ break;
+ case TCG_TYPE_I64:
+ if (ret < 32) {
+ tcg_out_mem_long(s, LD, LDX, ret, base, offset);
+ break;
+ }
+ /* fallthru */
+ case TCG_TYPE_V64:
+ tcg_debug_assert(ret >= 32);
+ assert((offset & 7) == 0);
+ tcg_out_mem_long(s, 0, LVX, ret & 31, base, offset);
+ if (offset & 8) {
+ tcg_out32(s, VSLDOI | VRT(ret) | VRA(ret) | VRB(ret) | (8 << 6));
+ }
+ break;
+ case TCG_TYPE_V128:
+ tcg_debug_assert(ret >= 32);
+ tcg_out_mem_long(s, 0, LVX, ret & 31, base, offset);
+ break;
+ default:
+ g_assert_not_reached();
}
- tcg_out_mem_long(s, opi, opx, ret, arg1, arg2);
}
-static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
- TCGReg arg1, intptr_t arg2)
+static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+ TCGReg base, intptr_t offset)
{
- int opi, opx;
+ int shift;
- tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
- if (type == TCG_TYPE_I32) {
- opi = STW, opx = STWX;
- } else {
- opi = STD, opx = STDX;
+ switch (type) {
+ case TCG_TYPE_I32:
+ if (arg < 32) {
+ tcg_out_mem_long(s, STW, STWX, arg, base, offset);
+ break;
+ }
+ assert((offset & 3) == 0);
+ shift = (offset - 4) & 0xc;
+ if (shift) {
+ tcg_out32(s, VSLDOI | VRT(TCG_VEC_TMP1)
+ | VRA(arg) | VRB(arg) | (shift << 6));
+ arg = TCG_VEC_TMP1;
+ }
+ tcg_out_mem_long(s, 0, STVEWX, arg & 31, base, offset);
+ break;
+ case TCG_TYPE_I64:
+ if (arg < 32) {
+ tcg_out_mem_long(s, STD, STDX, arg, base, offset);
+ break;
+ }
+ /* fallthru */
+ case TCG_TYPE_V64:
+ tcg_debug_assert(arg >= 32);
+ assert((offset & 7) == 0);
+ if (offset & 8) {
+ tcg_out32(s, VSLDOI | VRT(TCG_VEC_TMP1)
+ | VRA(arg) | VRB(arg) | (8 << 6));
+ arg = TCG_VEC_TMP1;
+ }
+ tcg_out_mem_long(s, 0, STVEWX, arg & 31, base, offset);
+ tcg_out_mem_long(s, 0, STVEWX, arg & 31, base, offset + 4);
+ break;
+ case TCG_TYPE_V128:
+ tcg_debug_assert(arg >= 32);
+ tcg_out_mem_long(s, 0, STVX, arg & 31, base, offset);
+ break;
+ default:
+ g_assert_not_reached();
}
- tcg_out_mem_long(s, opi, opx, arg, arg1, arg2);
}
static inline bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val,
@@ -2618,6 +2827,232 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
const TCGArg *args,
}
}
+int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
+{
+ switch (opc) {
+ case INDEX_op_and_vec:
+ case INDEX_op_or_vec:
+ case INDEX_op_xor_vec:
+ case INDEX_op_andc_vec:
+ case INDEX_op_not_vec:
+ return 1;
+ case INDEX_op_add_vec:
+ case INDEX_op_sub_vec:
+ case INDEX_op_smax_vec:
+ case INDEX_op_smin_vec:
+ case INDEX_op_umax_vec:
+ case INDEX_op_umin_vec:
+ case INDEX_op_ssadd_vec:
+ case INDEX_op_sssub_vec:
+ case INDEX_op_usadd_vec:
+ case INDEX_op_ussub_vec:
+ return vece <= MO_32;
+ case INDEX_op_cmp_vec:
+ return vece <= MO_32 ? -1 : 0;
+ default:
+ return 0;
+ }
+}
+
+static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
+ unsigned vecl, unsigned vece,
+ const TCGArg *args, const int *const_args)
+{
+ static const uint32_t
+ add_op[4] = { VADDUBM, VADDUHM, VADDUWM, 0 },
+ sub_op[4] = { VSUBUBM, VSUBUHM, VSUBUWM, 0 },
+ eq_op[4] = { VCMPEQUB, VCMPEQUH, VCMPEQUW, 0 },
+ gts_op[4] = { VCMPGTSB, VCMPGTSH, VCMPGTSW, 0 },
+ gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, 0 },
+ ssadd_op[4] = { VADDSBS, VADDSHS, VADDSWS, 0 },
+ usadd_op[4] = { VADDUBS, VADDUHS, VADDUWS, 0 },
+ sssub_op[4] = { VSUBSBS, VSUBSHS, VSUBSWS, 0 },
+ ussub_op[4] = { VSUBUBS, VSUBUHS, VSUBUWS, 0 },
+ umin_op[4] = { VMINUB, VMINUH, VMINUW, 0 },
+ smin_op[4] = { VMINSB, VMINSH, VMINSW, 0 },
+ umax_op[4] = { VMAXUB, VMAXUH, VMAXUW, 0 },
+ smax_op[4] = { VMAXSB, VMAXSH, VMAXSW, 0 };
+
+ TCGType type = vecl + TCG_TYPE_V64;
+ TCGArg a0 = args[0], a1 = args[1], a2 = args[2];
+ uint32_t insn;
+
+ switch (opc) {
+ case INDEX_op_ld_vec:
+ tcg_out_ld(s, type, a0, a1, a2);
+ return;
+ case INDEX_op_st_vec:
+ tcg_out_st(s, type, a0, a1, a2);
+ return;
+
+ case INDEX_op_add_vec:
+ insn = add_op[vece];
+ break;
+ case INDEX_op_sub_vec:
+ insn = sub_op[vece];
+ break;
+ case INDEX_op_ssadd_vec:
+ insn = ssadd_op[vece];
+ break;
+ case INDEX_op_sssub_vec:
+ insn = sssub_op[vece];
+ break;
+ case INDEX_op_usadd_vec:
+ insn = usadd_op[vece];
+ break;
+ case INDEX_op_ussub_vec:
+ insn = ussub_op[vece];
+ break;
+ case INDEX_op_smin_vec:
+ insn = smin_op[vece];
+ break;
+ case INDEX_op_umin_vec:
+ insn = umin_op[vece];
+ break;
+ case INDEX_op_smax_vec:
+ insn = smax_op[vece];
+ break;
+ case INDEX_op_umax_vec:
+ insn = umax_op[vece];
+ break;
+ case INDEX_op_and_vec:
+ insn = VAND;
+ break;
+ case INDEX_op_or_vec:
+ insn = VOR;
+ break;
+ case INDEX_op_xor_vec:
+ insn = VXOR;
+ break;
+ case INDEX_op_andc_vec:
+ insn = VANDC;
+ break;
+ case INDEX_op_not_vec:
+ insn = VNOR;
+ a2 = a1;
+ break;
+
+ case INDEX_op_dup_vec:
+ /* Recall we use VSX integer loads, so the integer is right
+ justified within the left (zero-index) double-word. */
+ switch (vece) {
+ case MO_8:
+ tcg_out32(s, VSPLTB | VRT(a0) | VRB(a1) | (7 << 16));
+ break;
+ case MO_16:
+ tcg_out32(s, VSPLTH | VRT(a0) | VRB(a1) | (3 << 16));
+ break;
+ case MO_32:
+ tcg_out32(s, VSPLTW | VRT(a0) | VRB(a1) | (1 << 16));
+ break;
+ case MO_64:
+ /* FIXME: 32-bit altivec */
+ tcg_out_dupi_vec(s, TCG_TYPE_V128, TCG_VEC_TMP1,
+ 0x0001020304050607ull);
+ tcg_out32(s, VPERM | VRT(a0) | VRA(a1) | VRB(a1)
+ | VRC(TCG_VEC_TMP1));
+ break;
+ }
+ return;
+
+ case INDEX_op_cmp_vec:
+ {
+ TCGCond cond = args[3];
+
+ switch (cond) {
+ case TCG_COND_EQ:
+ insn = eq_op[vece];
+ break;
+ case TCG_COND_GT:
+ insn = gts_op[vece];
+ break;
+ case TCG_COND_GTU:
+ insn = gtu_op[vece];
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ tcg_debug_assert(insn != 0);
+
+ tcg_out32(s, insn | VRT(a0) | VRA(a1) | VRB(a2));
+ }
+ return;
+
+ default:
+ g_assert_not_reached();
+ }
+
+ tcg_debug_assert(insn != 0);
+ tcg_out32(s, insn | VRT(a0) | VRA(a1) | VRB(a2));
+}
+
+static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0,
+ TCGv_vec v1, TCGv_vec v2, TCGCond cond)
+{
+ bool need_swap = false, need_inv = false;
+
+ tcg_debug_assert(vece <= MO_32);
+
+ switch (cond) {
+ case TCG_COND_EQ:
+ case TCG_COND_GT:
+ case TCG_COND_GTU:
+ break;
+ case TCG_COND_NE:
+ case TCG_COND_LE:
+ case TCG_COND_LEU:
+ need_inv = true;
+ break;
+ case TCG_COND_LT:
+ case TCG_COND_LTU:
+ need_swap = true;
+ break;
+ case TCG_COND_GE:
+ case TCG_COND_GEU:
+ need_swap = need_inv = true;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ if (need_inv) {
+ cond = tcg_invert_cond(cond);
+ }
+ if (need_swap) {
+ TCGv_vec t1;
+ t1 = v1, v1 = v2, v2 = t1;
+ cond = tcg_swap_cond(cond);
+ }
+
+ vec_gen_4(INDEX_op_cmp_vec, type, vece, tcgv_vec_arg(v0),
+ tcgv_vec_arg(v1), tcgv_vec_arg(v2), cond);
+
+ if (need_inv) {
+ tcg_gen_not_vec(vece, v0, v0);
+ }
+}
+
+void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
+ TCGArg a0, ...)
+{
+ va_list va;
+ TCGv_vec v0, v1, v2;
+
+ va_start(va, a0);
+ v0 = temp_tcgv_vec(arg_temp(a0));
+ v1 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
+ v2 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
+
+ switch (opc) {
+ case INDEX_op_cmp_vec:
+ expand_vec_cmp(type, vece, v0, v1, v2, va_arg(va, TCGArg));
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ va_end(va);
+}
+
static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
{
static const TCGTargetOpDef r = { .args_ct_str = { "r" } };
@@ -2655,6 +3090,9 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode
op)
= { .args_ct_str = { "r", "r", "r", "r", "rI", "rZM" } };
static const TCGTargetOpDef sub2
= { .args_ct_str = { "r", "r", "rI", "rZM", "r", "r" } };
+ static const TCGTargetOpDef v_r = { .args_ct_str = { "v", "r" } };
+ static const TCGTargetOpDef v_v = { .args_ct_str = { "v", "v" } };
+ static const TCGTargetOpDef v_v_v = { .args_ct_str = { "v", "v", "v" } };
switch (op) {
case INDEX_op_goto_ptr:
@@ -2790,6 +3228,31 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode
op)
return (TCG_TARGET_REG_BITS == 64 ? &S_S
: TARGET_LONG_BITS == 32 ? &S_S_S : &S_S_S_S);
+ case INDEX_op_add_vec:
+ case INDEX_op_sub_vec:
+ case INDEX_op_mul_vec:
+ case INDEX_op_and_vec:
+ case INDEX_op_or_vec:
+ case INDEX_op_xor_vec:
+ case INDEX_op_andc_vec:
+ case INDEX_op_orc_vec:
+ case INDEX_op_cmp_vec:
+ case INDEX_op_ssadd_vec:
+ case INDEX_op_sssub_vec:
+ case INDEX_op_usadd_vec:
+ case INDEX_op_ussub_vec:
+ case INDEX_op_smax_vec:
+ case INDEX_op_smin_vec:
+ case INDEX_op_umax_vec:
+ case INDEX_op_umin_vec:
+ return &v_v_v;
+ case INDEX_op_not_vec:
+ case INDEX_op_dup_vec:
+ return &v_v;
+ case INDEX_op_ld_vec:
+ case INDEX_op_st_vec:
+ return &v_r;
+
default:
return NULL;
}
@@ -2800,6 +3263,9 @@ static void tcg_target_init(TCGContext *s)
unsigned long hwcap = qemu_getauxval(AT_HWCAP);
unsigned long hwcap2 = qemu_getauxval(AT_HWCAP2);
+ if (hwcap & PPC_FEATURE_HAS_ALTIVEC) {
+ have_isa_altivec = true;
+ }
if (hwcap & PPC_FEATURE_ARCH_2_06) {
have_isa_2_06 = true;
}
@@ -2811,6 +3277,10 @@ static void tcg_target_init(TCGContext *s)
tcg_target_available_regs[TCG_TYPE_I32] = 0xffffffff;
tcg_target_available_regs[TCG_TYPE_I64] = 0xffffffff;
+ if (have_isa_altivec) {
+ tcg_target_available_regs[TCG_TYPE_V64] = 0xffffffff00000000ull;
+ tcg_target_available_regs[TCG_TYPE_V128] = 0xffffffff00000000ull;
+ }
tcg_target_call_clobber_regs = 0;
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R0);
@@ -2826,6 +3296,27 @@ static void tcg_target_init(TCGContext *s)
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R11);
tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R12);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V0);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V1);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V2);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V3);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V4);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V5);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V6);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V7);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V8);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V9);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V10);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V11);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V12);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V13);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V14);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V15);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V16);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V17);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V18);
+ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V19);
+
s->reserved_regs = 0;
tcg_regset_set_reg(s->reserved_regs, TCG_REG_R0); /* tcg temp */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_R1); /* stack pointer */
@@ -2836,6 +3327,8 @@ static void tcg_target_init(TCGContext *s)
tcg_regset_set_reg(s->reserved_regs, TCG_REG_R13); /* thread pointer */
#endif
tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP1); /* mem temp */
+ tcg_regset_set_reg(s->reserved_regs, TCG_VEC_TMP1);
+ tcg_regset_set_reg(s->reserved_regs, TCG_VEC_TMP2);
if (USE_REG_TB) {
tcg_regset_set_reg(s->reserved_regs, TCG_REG_TB); /* tb->tc_ptr */
}
--
2.17.2
- [Qemu-devel] [PATCH for-4.1 v2 02/13] tcg: Return bool success from tcg_out_mov, (continued)
- [Qemu-devel] [PATCH for-4.1 v2 02/13] tcg: Return bool success from tcg_out_mov, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 03/13] tcg: Support cross-class moves without instruction support, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 08/13] tcg/ppc: Implement INDEX_op_dupm_vec, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 07/13] tcg: Add INDEX_op_dup_mem_vec, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 09/13] tcg/ppc: Support vector shift by immediate, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 10/13] tcg/ppc: Support vector multiply, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 11/13] tcg/ppc: Update vector support to v2.06, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 06/13] tcg/ppc: Initial backend support for Altivec,
Richard Henderson <=
- [Qemu-devel] [PATCH for-4.1 v2 12/13] tcg/ppc: Update vector support to v2.07, Richard Henderson, 2019/03/17
- [Qemu-devel] [PATCH for-4.1 v2 13/13] tcg/ppc: Update vector support to v3.00, Richard Henderson, 2019/03/17
- Re: [Qemu-devel] [PATCH for-4.1 v2 00/13] tcg/ppc: Add vector opcodes, no-reply, 2019/03/17